返回
Reliable LLM-driven BIM automation through capability-based multi-dimensional evaluation
DOI:10.1016/j.autcon.2026.106910.png)
摘要
En 中文
• 六能力框架评估LLM在BIM自动化中的可靠性。
• 对31项BIM任务进行测试,涵盖组件、装配和系统复杂度。
• 十类错误;API误用是最常见的失败原因(48.3%)。
• MADM评分显示可靠性:0.603(组件),0.505(装配),0.489(系统)。
• LLM在调试方面表现强,但在语义推理和API逻辑方面较弱。
Keyword:
LLM reliability
BIM automation
capability framework
multi-dimensional evaluation
API misuse
期刊
IF:
11.5
论文数:
6.3K
被引数:
4.2W
机构
引用论文
Investigating the Use of ChatGPT for the Scheduling of Construction Projects调查ChatGPT在建设项目调度中的使用
BUILDINGS
IF3.1
Advancing BIM information retrieval with an LLM-based query-domain-specific language and library code function alignment system基于LLM的查询领域特定语言和库代码函数对齐系统推动BIM信息检索发展
A GPT-Powered Assistant for Real-Time Interaction with Building Information ModelsGPT支持的助手,用于与建筑信息模型进行实时交互
BUILDINGS
IF3.1
Exploring possibilities and limits of ChatGPT: Usage in building design studies探索ChatGPT的可能性与局限性:在建筑设计研究中的应用
A text dataset of fire door defects for pre-delivery inspections of apartments during the construction stage施工阶段公寓预交付检查用火灾门缺陷文本数据集
Real operational labeled data of air handling units from office, auditorium, and hospital buildings来自办公楼、礼堂和医院建筑物的空气处理单元的实际运行带标签数据
Scientific Data
IF6.9
Optimizing the Utilization of Generative Artificial Intelligence (AI) in the AEC Industry: ChatGPT Prompt Engineering and Design优化生成式人工智能(AI)在AEC行业中的应用:ChatGPT提示工程与设计
CivilEng
IF0
Joffe, I.; Felobes, G.; Elgouhari, Y.; Kalaleh, M.T.; Mei, Q.; Chui, Y.H. The Framework and Implementation of Using Large Language Models to Answer Questions about Building Codes and Standards. J. Comput. Civ. Eng. 2025, 39, 05025004. [Google Scholar] [CrossRef]Joffe, I.; Felobes, G.; Elgouhari, Y.; Kalaleh, M.T.; Mei, Q.; Chui, Y.H. 使用大型语言模型回答建筑规范和标准问题的框架与实现。J. Comput. Civ. Eng. 2025, 39, 05025004. [Google Scholar] [CrossRef]

